Manufacturing method of learning data, learning method, learning data manufacturing apparatus, learning apparatus, and memory medium

1. A manufacturing method of learning data used for making a neural network perform learning, the manufacturing method of learning data comprising:

a first acquiring step configured to acquire an original image;

a second acquiring step configured to acquire a first image as a training image generated by adding first blur to the original image; and

a third acquiring step configured to acquire a second image as a ground truth image generated by adding second blur to the original image,

wherein an amount of the second blur added to the original image is smaller than an amount of the first blur added to the original image, and

wherein the first blur and the second blur are acquired based on the same optical information.

2. The manufacturing method of learning data according to claim 1 , further comprising a fourth acquiring step configured to acquire the optical information,

wherein the optical information is a plurality of pieces of optical information each of which is different depending on an image height,

wherein the second acquiring step acquires the first image generated by adding the first blur using the plurality of pieces of optical information, and

wherein the third acquiring step acquires the second image generated by adding the second blur using the plurality of pieces of optical information.

3. The manufacturing method of learning data according to claim 1 ,

wherein the second image is generated by adding the second blur to the original image, the second blur having a different amount depending on an image height.

4. The manufacturing method of learning data according to claim 3 ,

wherein the second image is generated by adding the second blur with a third blur amount to a first image height of the original image, and by adding the second blur with a fourth blur amount larger than the third blur amount to a second image height higher than the first image height of the original image.

5. The manufacturing method of learning data according to claim 1 , further comprising a fourth acquiring step configured to acquire the optical information,

wherein the optical information is a plurality of pieces of optical information each of which is different depending on an image height,

wherein the second acquiring step acquires the first image which is generated by adding the first blur using optical information corresponding to an image height corresponding to the first image among the plurality of pieces of optical information, and

wherein the third acquiring step acquires the second image which is generated by adding the second blur using optical information corresponding to an image height corresponding to the second image among the plurality of pieces of optical information.

6. The manufacturing method of learning data according to claim 1 ,

wherein the amount of the second blur is acquired based on a luminance value.

7. The manufacturing method of learning data according to claim 6 ,

wherein when the luminance value is a first luminance value, the second image is generated by adding the second blur with a third blur amount to the original image, and

wherein when the luminance value is a second luminance value lower than the first luminance value, the second image is generated by adding the second blur with a fourth blur amount larger than the third blur amount to the original image.

8. A learning method that makes a neural network perform learning using learning data generated by the manufacturing method of learning data according to claim 1 , the learning method comprising steps of:

generating a processed image by inputting the first image as the training image into the neural network; and

updating the neural network based on the second image and the processed image.

9. A non-transitory computer-readable storage medium storing a computer program that causes a computer to execute the manufacturing method of learning data according to claim 1 .

10. A manufacturing method of learnt model that manufactures a learnt model by making a neural network perform learning using learning data generated by the manufacturing method of learning data according to claim 1 , the manufacturing method of learnt model comprising steps of:

generating a processed image by inputting the first image as the training image into the neural network; and

making the neural network perform learning based on the second image and the processed image.

11. An image processing method comprising steps of:

acquiring the neural network obtained by the manufacturing method according to claim 10 ;

generating an estimated image by inputting an input image into the neural network.

12. The image processing method according to claim 11 ,

wherein the input image is an image obtained by image pickup, and

wherein the estimated image is generated by correcting blur in the input image generated in the image pickup by the neural network.

13. A non-transitory computer-readable storage medium storing a computer program that causes a computer to execute the image processing method according to claim 11 .

14. An image processing apparatus comprising at least one processor or circuit configured to execute a plurality of tasks including:

an acquisition task configured to acquire the neural network obtained by the manufacturing method according to claim 10 ; and

a generation task configured to estimate an estimated image by inputting an input image into the neural network.

15. A learning data manufacturing apparatus which manufactures learning data used for learning of a neural network, the learning data manufacturing apparatus comprising at least one processor or circuit configured to execute a plurality of tasks including:

a first acquisition task configured to acquire an original image;

a second acquisition task configured to acquire a first image generated by adding first blur to the original image; and

a third acquisition task configured to acquire a second image generated by adding second blur to the original image,

wherein an amount of the second blur added to the original image is smaller than an amount of the first blur added to the original image, and

wherein the first blur and the second blur are acquired based on the same optical information.

16. A learning apparatus comprising:

the learning data manufacturing apparatus according to claim 15 ; and

at least one processor or circuit configured to execute a plurality of tasks including:

a generation task configured to generate a processed image by inputting the first image as the training image to a neural network; and

an update task configured to update the neural network based on the second image and the processed image.